鸡蛋蛋壳裂纹的模式识别

Identification of eggshell crack by pattern recognition

鸡蛋被敲击激励后,将传感器获得的时域信号进行频域特征分析后发现:无损蛋的频域特征曲线有明显的主频率值、峰值突出,而有裂纹蛋没有明显的主频率值。在归一化功率谱中,分别按'间隔频率提取幅值'、'依次高低取幅值'和'幅值高低依次提取频率'等方法来获取前10个或前20个特征值后,进行了主成分分析和线性判别分析,结果发现:采用间隔频率提取的幅值来判别裂纹蛋与完好蛋效果较差,采用幅值高低依次提取的频率来判别的效果最好;采用20个特征值经主成分分析和线性判别分析区分的效果分别均不如采用10个特征值的区分效果;线性判别分析区分的效果优于主成分分析区分的效果。

An egg is excited by a light mechanical impact on different locations of the eggshell,then the cracks are deteted by dynamical frequency response using flexible piezoelectric film sensors.Analyse show that the dominant resonance frequency can be observed and the frequency value is lower in the intact eggs.While for cracked eggs,there are several peak frequencies,the magnitudes of these frequencies are approximate,and the frequency value is higher.In normalization average of frequency domain,10 or 20 magnitudes of interval frequency,10 magnitudes in turn and frequencies by magnitude in turn are extracted as eigenvalues.Principal Component Analysis（PCA）and Linear Discriminant Analysis（LDA）are used to investigate whether the dynamical frequency response is able to distinguish intact egg from cracked egg.Results show that the frequency response could distinguish the intact egg from the cracked egg using LDA and PCA based on magnitudes in turn and frequencies by magnitude in turn,and higher distinguish rate can be obtained based on frequencies by magnitude in turn.Also higher distinguish rate can be obtained using LDA or based on 10 eigenvalues.